© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16603
    Prev
    Next
    INDEX
    Explanations

    tired of X or tired and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    悧
    -1.95
     thankfully
    -1.91
     But
    -1.84
    珹
    -1.82
    君は
    -1.78
    谖
    -1.75
    
    -1.70
    曁
    -1.69
     begun
    -1.66
    
    -1.66
    POSITIVE LOGITS
    🐾
    2.08
    ⤵
    1.98
    .
    1.95
    😴
    1.91
    枇
    1.83
    titud
    1.81
    😫
    1.81
    ⬇
    1.79
    '--
    1.79
    ⬇️
    1.77
    Activations Density 0.010%

    No Known Activations